Open AccessEffect of Transportation Parameters on Traffic Accident in Urban Areas Comparison study of ANFIS With Statistical Analysis
Author(s) -
Ghassan Suleiman,
Mohammad K. Younes,
Murat Ergün,
Khaled Al Omari
Publication year - 2021
Publication title -
international journal of safety and security engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.202
H-Index - 10
eISSN - 2041-904X
pISSN - 2041-9031
DOI - 10.18280/ijsse.110201
Subject(s) - transport engineering , adaptive neuro fuzzy inference system , metropolitan area , negative binomial distribution , trips architecture , regression analysis , statistics , data collection , geography , fuzzy logic , computer science , engineering , mathematics , fuzzy control system , archaeology , artificial intelligence , poisson distribution
Traffic accidents present a serious problem for both developed and developing countries and have become an urgent matter to tackle in all large metropolitan areas. This study aims to perform a deep comprehensive analysis of the traffic accidents issue in Istanbul, one of the world’s most populous cities. The accidents were classified and its intensities were presented on Istanbul map using a GIS tool. Furthermore, the performance of Negative Binomial Regression analysis and Adaptive Neuro-Fuzzy Inference System (ANFIS) model was assessed. Data collection of independent variables included distribution of trips, percentage of street parking, rate of car ownership, street density and population density. Trips were divided into three categories, passenger car, minibus and bus trips. The results showed that four legs intersection got the highest proportion of accidents among the other types with (40%). It also demonstrated that increasing both the percentage of bus trips and the percentage of street parking will decrease the traffic accident rate. Furthermore, the implementation of ANFIS model increased the accuracy of forecasts and reduced errors more than the regression model.